FreeBSD 5.4+SMP, severe network degredation

[Benson Wong]

I've been having similar issues after upgrading to the latest
5.4-STABLE. I used to have it running 5.4-STABLE with the GENERIC PAE
kernel. I rebuilt the world, and the kernel and now my bge (1Gbit)
gets a lot of "watchdog timeout -- resetting" issues.

I have acpi enabled in my kernel as well, perhaps this is also
affecting my server. I can't remember if the config has ACPI enabled
in the kernel. The only other difference I found in my old kernel
(PAE) configs and the generic one that comes with 5.4 is:

nodevice ehci (enhanced USB driver).

I'll try it with the NODEVICE ehci first and see if that fixes the
load / card issues. If not I'll try it with no acpi.

Thanks for the info.

On 7/28/05, dpk <dpk at dpk.net> wrote:
> Woah. Well, I guess I didn't try *everything*. Removing "device acpi" from
> the kernel config leaves me witih a PAE+SMP kernel that works fine. I can
> fetch files at wire speed and everything.
> 
> So, I guess this issue is closed. acpi was the ultimate culprit.
> 
> On Thu, 28 Jul 2005, dpk wrote:
> 
> > By the way, I also compared GENERIC performance against GENERIC w/
> > "options SMP" added, and had the same results.
> >
> > On Wed, 27 Jul 2005, dpk wrote:
> >
> > > We just received several SuperMicro servers, 3.0Ghz Xeon x 2, 4GB RAM.
> > > They're using the em driver and the ports are set to 1000Mbit (we also
> > > tried 100Mbit/full duplex on the card and on the switch). They're running
> > > FreeBSD 5.4.
> > >
> > > I ran a steady ping on a couple of them while they were running "GENERIC",
> > > and then rebooted them with a kernel built with the "PAE" kernel included
> > > with the installation, with "option SMP" added.
> > >
> > > The PAE-SMP-GENERIC kernel was built after cvsup'ing with "tag=RELENG_5_4"
> > > and the uname reports "5.4-RELEASE-p5".
> > >
> > > Here are the ping results:
> > >
> > > GENERIC:
> > >
> > > 117 packets transmitted, 117 packets received, 0% packet loss
> > > round-trip min/avg/max/stddev = 0.451/0.554/0.856/0.059 ms
> > >
> > > PAE-SMP-GENERIC:
> > >
> > > 102 packets transmitted, 102 packets received, 0% packet loss
> > > round-trip min/avg/max/stddev = 0.569/4.262/7.944/2.065 ms
> > >
> > > Fetching a 637MB ISO from a local server, also on 100/FDX:
> > >
> > > GENERIC:
> > >
> > > /dev/null                                     100% of  637 MB   10 MBps 00m00s
> > >
> > > real    0m58.071s
> > > user    0m1.954s
> > > sys     0m6.278s
> > >
> > > PAE-SMP-GENERIC:
> > >
> > > /dev/null                                     100% of  637 MB 5764 kBps 00m00s
> > >
> > > real    1m53.324s
> > > user    0m1.478s
> > > sys     0m5.624s
> > >
> > > Running GENERIC, systat shows about 7000 interrupts/second, and around 600
> > > interrupts/second using PAE-SMP-GENERIC, while fetch was running.
> > >
> > > I've checked the errata and hardware notes, as well as gnats, and was not
> > > able to find anything that explains or matches this behavior. We've run
> > > SMP servers for years, using 4.5-4.11, but we've never seen the network
> > > performance cut in half (or pings go up 10x).
> > >
> > > Removing "option SMP" makes the problem go away, but at a very significant
> > > performance cost obviously.
> > >
> > > Could it be something from -p5? Is this explained/examined in a PR I've
> > > missed, and if so can I add some information?
> > >
> >
> _______________________________________________
> freebsd-questions at freebsd.org mailing list
> http://lists.freebsd.org/mailman/listinfo/freebsd-questions
> To unsubscribe, send any mail to "freebsd-questions-unsubscribe at freebsd.org"
> 


-- 
blog: http://www.mostlygeek.com